DSH插件商店

dsh-think-translate

UncleK

Thinking-chain UI translation for DeepSeek Harness: 8 target languages, local Ollama model primary with in-panel download, Google/Bing fallback

dsh-llm-ollama

NOirBRight

Native Ollama Cloud provider and Web configuration plugin for DeepSeek Harness

dsh-fetch-timeouts

d3vmeh

DeepSeek Harness plugin: raise Node's HTTP timeouts process-wide so slow local models (Ollama, LM Studio) are not cut off at 5 minutes

dsh-llm-ollama

1035041186

dsh-llm-ollama 是一个为 DeepSeek Harness（dsh）开发的社区插件，让 Harness 通过 Ollama 原生协议（/api/chat） 接入本地 Ollama 服务。即插即用：不改动 dsh 官方任何文件，安装后自动在「设置」中多出一个 Ollama 页面，并在会话模型选择器中提供该提供方的模型。

dsh-web-search-ollama

sryimnoob123

Ollama-backed web search provider for DeepSeek Harness (ctx.web)

tokilake-ai-gateway

Tokimorphling

Self-hosted AI gateway for distributed local LLM GPUs. OpenAI-compatible API with NAT traversal, WebSocket/QUIC tunnels, Ollama/vLLM/SGLang workers.

dsh-wsl-ollama

173787247

Local Ollama status / list / chat / embed for dsh on WSL.

DSH-LocalModels-TokenSavior

Movingelated

DSH (DeepSeek Harness) plugin: delegate read-only collection tasks to a local Ollama model — zero cloud token cost, zero API key. 把只读采集任务交给本机 Ollama 模型：含设置面板 + 选型尺 + AI 可读说明书。

dsh-gpu-cleanup

princepainter

DeepSeek Harness Web UI plugin: adds a 'Release GPU' button to free VRAM by unloading local Ollama models

dsh-auto-continue

zhou1736948757-cpu

Automatically resumes replies cut off at the output token limit — built for self-hosted Ollama users with small output caps. · 回答被输出上限截断时自动续写，面向自部署 Ollama 用户。